no code implementations • 15 Jun 2021 • David McNeely-White, Ben Sattelberg, Nathaniel Blanchard, Ross Beveridge
When instead evaluating embeddings generated from two CNNs, where one CNN's embeddings are mapped with a linear transformation, the mean true accept rate drops to 0. 95 using the same verification paradigm.
no code implementations • 5 Oct 2020 • David McNeely-White, Benjamin Sattelberg, Nathaniel Blanchard, Ross Beveridge
When image embeddings generated by one CNN are transformed into embeddings corresponding to the feature space of a second CNN trained on the same task, their respective image classification or face verification performance is largely preserved.